Uncertainty quantification in neural network classifiers -- a local linear approach

DOI10.1016/J.AUTOMATICA.2024.111563MaRDI QIDQ6546838zbMATH OpenWikidataFDO

Authors Magnus Malmström, Isaac Skog, Daniel Axehill, Fredrik Gustafsson

Publication date 30 May 2024

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2024.111563

zbMATH Keywords

identification and model reductioninformation and sensor fusionneural networksuncertainty descriptions

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Uncertainty of feed forward neural networks recognizing quantum contextuality
• Epistemic uncertainty quantification in deep learning classification by the delta method
• Neural Network Uncertainty Assessment Using Bayesian Statistics: A Remote Sensing Application
• Can a single neuron learn predictive uncertainty?

Cites work

• Bayesian frequentist bounds for machine learning and system identification
• Deep learning
• Introduction to statistical limit theorem
• Machine learning. A first course for engineers and scientists
• On the sensitivity of pose estimation neural networks: rotation parameterizations, Lipschitz constants, and provable bounds
• Pattern recognition and machine learning.
• Prediction Intervals for Artificial Neural Networks
• Robust distributed maximum likelihood estimation with dependent quantized data
• Strictly Proper Scoring Rules, Prediction, and Estimation

Cited in

(2)

• Uncertainty of feed forward neural networks recognizing quantum contextuality
• Can a single neuron learn predictive uncertainty?

This page was built for publication: Uncertainty quantification in neural network classifiers -- a local linear approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6546838)